© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116945
    Prev
    Next
    INDEX
    Explanations

    insulting or humiliating things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /etc
    -0.10
     pornstar
    -0.10
     wink
    -0.09
    Rails
    -0.09
     sama
    -0.09
     playable
    -0.09
    ivic
    -0.08
    867
    -0.08
     eens
    -0.08
    /#
    -0.08
    POSITIVE LOGITS
     insulting
    0.11
     humili
    0.11
     humiliating
    0.11
     mistress
    0.11
     âĤ¬
    0.11
     »
    0.11
     Nr
    0.11
     disrespectful
    0.11
     stom
    0.11
     rev
    0.10
    Activations Density 0.005%

    No Known Activations